Papers › Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

18 Nov 2015CVPR 2016 6arXiv:1511.05756archive 2025-07-28

Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han

We tackle image question answering (ImageQA) problem by learning a convolutional neural network (CNN) with a dynamic parameter layer whose weights are determined adaptively based on questions. For the adaptive parameter prediction, we employ a separate parameter prediction network, which consists of gated recurrent unit (GRU) taking a question as its input and a fully-connected layer generating a set of candidate weights as its output. However, it is challenging to construct a parameter prediction network for a large number of parameters in the fully-connected dynamic parameter layer of the CNN. We reduce the complexity of this problem by incorporating a hashing technique, where the candidate weights given by the parameter prediction network are selected using a predefined hash function to determine individual weights in the dynamic parameter layer. The proposed network---joint network with the CNN for ImageQA and the parameter prediction network---is trained end-to-end through back-propagation, where its weights are initialized using a pre-trained CNN and GRU. The proposed algorithm illustrates the state-of-the-art performance on all available public ImageQA benchmarks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

HyeonwooNoh/DPPnet mentioned on GitHubtorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Retrieval with Multi-Modal QueryParameter PredictionPredictionQuestion AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval with Multi-Modal Query Fashion200k Param Hashing Recall@1 12.2 #7 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Param Hashing Recall@10 40 #7 of 8 Archive leaderboard report
Image Retrieval with Multi-Modal Query Fashion200k Param Hashing Recall@50 61.7 #7 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GRU

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections